Cumincad : CUMINCAD Papers : Search Results

CumInCAD is a Cumulative Index about publications in Computer Aided Architectural Design
supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD and CAAD futures

PDF papers
References

Hits 1 to 20 of 360

Reformat results as: short short into frame detailed detailed into frame

_id	ijac202322101
id	ijac202322101
authors	Mizobuti, Vinicius; Gabriela Lamanna Soares, Antonio Carlos Laraia Figueira de Mello
year	2024
title	Encapsulating creative collaborations: A case study in the design of cement tiles
source	International Journal of Architectural Computing 2024, Vol. 22 - no. 1, 1-25
summary	Advances in computer-aided architectural design led to an increased interest in the field for cross-disciplinary creative collaborations. However, this process rarely accounts for the agents outside of the discipline’s intellectual framework, such as craftsmen, failing to include existing production capabilities in the digital transformation of the industry. To tackle this issue, we investigate an approach that implements encapsulated instruments as enablers of creative collaborations between computational designers and craftsmen. We evaluate this approach by designing three cement tile models, a traditional handmade construction element used in Brazil. The results demonstrate that encapsulated instruments expand the craft’s design space through creative decisions operated by the craftsman, and interviews with the tile makers elaborate on their perceived change in creative agency, identifying limitations when disrupting social roles and hierarchical relationships in craftsmanship. Results also raise opportunities for expanding this approach at other scales and systems, helping to democratize and distribute design knowledge.
keywords	Computational making, creative design, digital fabrication, low-high architecture, technological appropriation
series	journal
last changed	2024/07/18 13:03

_id	ecaade2024_353
id	ecaade2024_353
authors	Gschweitl, Lukas; Lang-Raudaschl, Matthias; Daleyev, Dalel; Stavric, Milena
year	2024
title	ReUse with BIM: Connecting architectural salvage centres to your BIM software
doi	https://doi.org/10.52842/conf.ecaade.2024.2.009
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 2, pp. 9–16
summary	This paper examines the potential for enhancing the efficiency of planning with ReUse Components (RUCs) in construction projects. It discusses the current practices, focusing on how Digital Salvage Centres (DSCs) can contribute to the trade of RUCs. The paper identifies challenges in the current workflow, such as the manual matching process and the lack of standardized interfaces with Building Information Modelling (BIM) software. It proposes a streamlined approach for integrating RUC data into BIM models automatically. The method involves web scraping, data validation, and the generation of Industry Foundation Classes (IFC) entities. The paper concludes by discussing the potential impact of the proposed approach and outlining future research directions, including the development of a functional prototype and collaboration with DSCs.
keywords	Reuse, Design by availability, Architectural salvage centre, Digital salvage centre, Design for circularity
series	eCAADe
email
last changed	2024/11/17 22:05

_id	ecaade2024_201
id	ecaade2024_201
authors	Hashizume, Keiji; Fukuda, Tomohiro; Yabuki, Nobuyoshi
year	2024
title	A Surface Modeling Method for Indoor Spaces from 3D Point Cloud Reconstructed by 3D Gaussian Splatting
doi	https://doi.org/10.52842/conf.ecaade.2024.1.695
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 1, pp. 695–704
summary	Building information modeling (BIM) is becoming increasingly important in architectural projects, and the implementation of BIM in new construction projects is progressing. On the other hand, many existing buildings do not have BIM data, so it is necessary to create it from scratch. A common method for converting existing buildings to BIM is scan-to-BIM, using techniques such as laser scanning or photogrammetry. However, laser scanning provides accurate point cloud data but requires expensive equipment, while photogrammetry is generally cost-effective but has lower accuracy point cloud data. Another approach for creating BIM from 2D images is to use neural radiance fields (NeRF). However, NeRF faces challenges in terms of data accuracy and processing speed when dealing with large or complex scenes. In contrast, 3D Gaussian Splatting is an emerging computer vision technology that uses machine learning to reconstruct 3D scenes from 2D images faster than NeRF, with comparable or better quality. Therefore, this study proposes a method to create surface models consisting of floors, walls, and ceilings as a preliminary step to creating BIM data for existing indoor spaces using 3D Gaussian Splatting. First, point cloud is generated using 3D Gaussian Splatting, followed by noise reduction. The point cloud is then classified based on height. Subsequently, processing such as extraction of boundary primitives from the point cloud of the floor and classification of feature points are performed to estimate the shape of the floor. Finally, ceilings and walls are created based on height and floor shape. The results of validation confirm an error of between 0.01m and 0.5m in the generated surface models. This study proposes a novel attempt to create 3D models using 3D Gaussian Splatting, contributing to the generation of BIM data for existing buildings.
keywords	Point Cloud, 3D Gaussian Splatting, Scan2BIM, Surface Modeling, Indoor 3D Reconstruction
series	eCAADe
email
last changed	2024/11/17 22:05

_id	caadria2024_234
id	caadria2024_234
authors	Xiong, Shuyan, Zea Escamilla, Edwin and Habert, Guillaume
year	2024
title	Uncovering the Circular Potential: Estimating Material Flows for Building Systems Components Reuse in the Swiss Built Environment
doi	https://doi.org/10.52842/conf.caadria.2024.1.545
source	Nicole Gardner, Christiane M. Herr, Likai Wang, Hirano Toshiki, Sumbul Ahmad Khan (eds.), ACCELERATED DESIGN - Proceedings of the 29th CAADRIA Conference, Singapore, 20-26 April 2024, Volume 1, pp. 545–554
summary	The construction industry plays a critical role in global resource consumption and greenhouse gas emissions, highlighting the urgent need for sustainable development practices. However, a key challenge in this area is the lack of effective models for resource use that align with circular economy principles. This gap hinders efforts to achieve sustainable resource management, especially in the face of increasing urbanization and material demand. To address this issue, our study presents a Parametric Predictive Model (PPM) to improve resource efficiency, specifically targeting the often-underestimated building systems. The model takes a bottom-up approach, utilizing local databases to accurately assess material stocks of building systems, thereby improving the granularity of data on material composition. Using advanced machine learning algorithms, the model processes both categorical and non-categorical data. The output, an enriched comprehensive database can support more informed decision making in sustainable resource recovery and allocation, but also contribute to the broader goals of reducing waste and promoting resource efficiency in the built environment.
keywords	Building Systems, Building Stock Modelling, Predictive Model, Circular Economy, Parametric Model
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	caadria2024_514
id	caadria2024_514
authors	Yildiz, Burak, Cuartero, Javier, Mostafavi, Fatemeh and Khademi, Seyran
year	2024
title	BatchPlan: A Large Scale Solution for Floor Plan Extraction
doi	https://doi.org/10.52842/conf.caadria.2024.1.201
source	Nicole Gardner, Christiane M. Herr, Likai Wang, Hirano Toshiki, Sumbul Ahmad Khan (eds.), ACCELERATED DESIGN - Proceedings of the 29th CAADRIA Conference, Singapore, 20-26 April 2024, Volume 1, pp. 201–210
summary	The development of Building Information Modelling (BIM) has enabled new opportunities, such as standard data storage and collaborative building design. Moreover, there exist many Life Cycle Assessment (LCA) tools and Building Energy Performance (BEP) simulators that use the Industry Foundation Classes (IFC) exports of BIM platforms as input for further operational analysis. While the extracted IFC files contain numerical and tabular data from the BIM model, the visual data including floor plans and section drawings is often obtained directly from the original 3D software such as REVIT. In this study, we introduce an open-source solution, BatchPlan, for batch processing IFC files of medium- and high-rise building projects, leading to floor plan extraction on a large scale. Furthermore, we have designed a user-friendly graphical interface that allows users to select floors manually. BatchPlan is based on open-source Python packages; thus users can easily edit and adapt it to their specific requirements. The presented solution enables a scalable data generation pipeline for downstream tasks that require extensive quantitative analysis, such as machine learning models to perform material detection, volume estimation, and environmental impact prediction.
keywords	floor plan extraction, Industry Foundation Classes (IFC), Building Information Modelling (BIM), architectural technical drawings, big data
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	ecaade2024_99
id	ecaade2024_99
authors	Ennemoser, Benjamin
year	2024
title	Human-Machine Collaboration as a Concept for Hybrid Digital and Analog Fabrication and shared Intelligence between Desktop Robotics, Mycelium and Humans
doi	https://doi.org/10.52842/conf.ecaade.2024.1.065
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 1, pp. 65–74
summary	This study examines the use of natural materials combined with advanced desk-top robotic fabrication in the AEC industry, aiming to reduce CO2 emissions and embodied carbon through sustainable practices. It investigates the use of desktop robotics to create complex rope structures, reinforced with mycelium, blending human and machine efforts. Traditional ropemaking is integrated with digital techniques, including procedural modeling and mycelium cultivation, to innovate fabrication methods. The research highlights a 20-25% increase in structural rigidity through mycelium reinforcement, tackling digital-physical alignment challenges and via photogrammetry, augmented reality, and digital twins. Results suggest the viability of small-scale robotics for sustainable construction, particularly in re-source-abundant rural areas, despite limitations in robot capacity. The study promotes sustainable building practices in the AEC sector, emphasizing human-machine collaboration and natural materials, setting the stage for future exploration in robotic applications and sustainable methodologies
keywords	Robotic Fabrication, Human-Machine Collaboration, Digital Twin, Augmented Reality, Desktop Robotics, Mycelium
series	eCAADe
email
last changed	2024/11/17 22:05

_id	caadria2024_524
id	caadria2024_524
authors	Castelo-Branco, Renata, Caetano, Ines and Leitao, António
year	2024
title	Algorithmic design explained: Decomposing parametric 3D problems into 2D visual illustrations
doi	https://doi.org/10.52842/conf.caadria.2024.3.009
source	Nicole Gardner, Christiane M. Herr, Likai Wang, Hirano Toshiki, Sumbul Ahmad Khan (eds.), ACCELERATED DESIGN - Proceedings of the 29th CAADRIA Conference, Singapore, 20-26 April 2024, Volume 3, pp. 9–18
summary	Algorithmic Design (AD) is a promising approach that merges two distinct processes - design thinking and computational thinking. However, it requires converting design concepts into algorithmic descriptions, which not only deviates from architecture's visual nature, but also tends to result in unstructured programs that are difficult to understand. Sketches or diagrams can help explain AD programs by capitalizing on their geometric nature, but they rapidly become outdated as designs progress. In ongoing research, an automatic illustration system was proposed to reduce the effort associated with updating 2D diagrams as ADs evolve. This paper discusses the ability of this system to improve the comprehension of AD programs that represent complex 3D architectural structures. To understand how to best explain parametric 3D models using 2D drawings, this research explores problem decomposition techniques, applying them in the visual documentation of two case studies, where illustration aids different comprehension scenarios: illustrating for future use, and illustrating while designing as part of the AD process.
keywords	algorithmic design, automatic illustration, design documentation, design representation
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	caadria2024_410
id	caadria2024_410
authors	Das, Avishek, Fich, Lars Brorson and Madsen, Claus B.
year	2024
title	A Comparative Analysis of Different Locomotion in Virtual Reality and Their Consequence in Spatial Cognition
doi	https://doi.org/10.52842/conf.caadria.2024.3.361
source	Nicole Gardner, Christiane M. Herr, Likai Wang, Hirano Toshiki, Sumbul Ahmad Khan (eds.), ACCELERATED DESIGN - Proceedings of the 29th CAADRIA Conference, Singapore, 20-26 April 2024, Volume 3, pp. 361–370
summary	Perception of space is deeply linked with our movement in space. In architectural design practices, this movement can be performed as a form of embodiment through the models of different scales and scoping into them with or without some apparatus. Leveraging the affordances of the model and the possibilities through the body architects perceive a scaled abstraction of the actual space. But in the case of virtual reality (VR), these movements bodily autonomy, and freedom are restricted due to the limitations of space and locomotion affordances. This paper will compare these three locomotion techniques and their effect on spatial cognition and navigation. We have developed a spatial navigation task for the participants of the architectural background to study the effect of different locomotive affordances. These different affordances have been utilised both in isolation and in combination with other affordances to study spatial navigation and cognition. Combining different guidelines aimed at reducing vection-induced motion sickness (VIMS) we have developed these environments and examined the degree of presence and spatial cognition concluding that a combination of different locomotive affordances can enhance the architectural experience and spatial cognition of the space.
keywords	virtual reality, architecture, locomotion, movement, spatial cognition
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	architectural_intelligence2024_24
id	architectural_intelligence2024_24
authors	Giuseppe Bono
year	2024
title	Text-to-building: experiments with AI-generated 3D geometry for building design and structure generation
doi	https://doi.org/https://doi.org/10.1007/s44223-024-00060-5
source	Architectural Intelligence Journal
summary	The paper seeks to investigate novel potentials for building design and structure generation that arise at the intersection of computational design and AI-generated 3D geometries. Although the use of AI technologies is exponentially increasing inside the architectural discipline, the design of spatial building configurations using AI-generated 3D geometries is still limited in its applications and represents an ongoing field of investigation in advanced architectural research. In this regard, several questions still need to be answered: how can we design new building typologies from AI-generated 3D geometries? And how can we use these typologies to shape both the real and the virtual world? The paper proposes a new approach to architectural design where artificial intelligence is used as the starting point for design exploration, while computational design procedures are employed to convert AI-generated 3D geometries into building elements – such as columns, beams, horizontal and vertical surfaces. The paper starts with a general overview of the current use of artificial intelligence inside the architectural discipline, and then it moves towards the explanation of specific AI generative models for 3D geometry reconstruction and representation. Subsequently, the proposed working pipeline is analysed in more detail – from the creation of 3D geometries using generative AI models to the conversion of such geometries into building elements that can be further designed and optimised using computational design tools and methods. The results shown in the paper are achieved using Shap-E as the main AI model, though the proposed pipeline can be implemented with multiple AI models. The paper ends by showing some of the generated results, finally adding some considerations to the relationship between human and artificial creativity inside the architectural discipline. The work presented in the paper suggests that the use of computational design tools and methods combined with the tectonics of the latent space opens new opportunities for topological and typological explorations. In a time where traditional architectural typologies are moving towards stagnation due to their inability to satisfy new human needs and ways of living, exploring AI-based working pipelines related to architectural design allows the definition of new design solutions for the generation of new architectural spaces. In doing so, the serendipitous aspect of AI biases is used as an auxiliary force to inform design decisions, promoting the discovery of a new inbuilt dynamism between human and artificial creativity. In a time where AI is everywhere, understanding the measure of such dynamism represents a key aspect for the future of the architectural discipline.
series	Architectural Intelligence
email
last changed	2025/01/09 15:05

_id	ecaade2024_306
id	ecaade2024_306
authors	Gu, Sijia; Yuan, Philip F.
year	2024
title	Research on Autonomous Recognition and Gripping Method for Robotic Fabrication of Heterogeneous Masonry Based on Computer Vision
doi	https://doi.org/10.52842/conf.ecaade.2024.1.127
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 1, pp. 127–136
summary	The emphasis on material diversity in robotic fabrication processes enhances the freedom of design in form and function, enabling the possibility of masonry working as functionally graded materials. However, in the robotic fabrication process based on offline programming, the lack of autonomous judgment of brick materials restricts the fabrication of multi-material masonry, resulting in additional labor and equipment costs. In this context, improving the autonomous judgment ability of construction robots on materials becomes an important breakthrough point, for which computer vision is a possible solution. However, current research on brick materials based on object detection mainly focuses on crack inspection and cannot distinguish multiple types of bricks in the same fabrication process. Therefore, the research aims to establish a methodology for an automatic multi-material brick grasping process based on the plane. The method consists of three parts: target detection, data conversion, and robot grasping. In this process, the research aims to innovate in four aspects: targets of object detection, derivation of dataset structure, introduction of design models, and real-world physical validation. Based on the proposal, a full-stage validation experiment was conducted. The experimental results validate the feasibility of the proposed method, hoping to bring new insights to robotic fabrication and parametric masonry design.
keywords	Robotic Fabrication, Heterogeneous Masonry, Computer Vision, Deep Learning
series	eCAADe
email
last changed	2024/11/17 22:05

_id	caadria2024_64
id	caadria2024_64
authors	Hadiatmadja, Juniarto
year	2024
title	Review on the Use of Conversational AI NPC Avatars in Teaching and Learning BIM: A Preliminary Observation of Its Introduction in a Built Environment Related Course in Singapore
doi	https://doi.org/10.52842/conf.caadria.2024.1.261
source	Nicole Gardner, Christiane M. Herr, Likai Wang, Hirano Toshiki, Sumbul Ahmad Khan (eds.), ACCELERATED DESIGN - Proceedings of the 29th CAADRIA Conference, Singapore, 20-26 April 2024, Volume 1, pp. 261–270
summary	Abilities in the use of BIM are critically needed in many industries but there are major challenges to current BIM training. It is unrealistic to assume that the current predominantly teacher directive mode of BIM training is sufficient or responsive enough to tackle rapidly changing challenges and cater to individual pursuits. This article reviews the findings of a research deploying conversational AI NPC avatars and BIM models in a game engine environment as a complementary learning tool that is non-directive and more enquiry based in nature. Enabling learners to autonomously converse and spatially direct the avatar movements to parts of the BIM model they wish to focus on. This article answers some ways the use of AI NPC avatars could benefit the learning of students that are newly introduced to BIM. The research compares tangible results as well as the learner's perceptions toward the use AI NPC avatars. The findings shed light on the technology's current utility and limitations in various aspects of the current topic. Some directions for development of future related research will be also be discussed.
keywords	BIM training, conversational AI NPC avatars, game engine environment, individual enquiry, learning tools
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	caadria2024_199
id	caadria2024_199
authors	Huang, Yulu, Song, Qiwei and Qiu, Waishan
year	2024
title	Do Visually Perceived Design Qualities Influence Dockless Bikeshare Cycling Routes? A Case Study of Ithaca Using GPS Trajectories
doi	https://doi.org/10.52842/conf.caadria.2024.2.099
source	Nicole Gardner, Christiane M. Herr, Likai Wang, Hirano Toshiki, Sumbul Ahmad Khan (eds.), ACCELERATED DESIGN - Proceedings of the 29th CAADRIA Conference, Singapore, 20-26 April 2024, Volume 2, pp. 99–108
summary	Understanding the influences of the built environment (BE) characteristics on the dockless bike-sharing system (DBS) is crucial for supporting and developing sustainable transportation mode. Previous studies on DBS cycling have primarily investigated the effects of macro-level BE characteristics (e.g., land use) or limited street features (e.g., greenery), overlooking that of perceived street design qualities such as enclosure. To better understand whether and how street-level environment characteristics, especially perceived street design qualities, influence DBS cycling routes, we calculate cycling volume based on GPS trajectories in Ithaca, a small town in New York State, and then quantify visual features and perceived design qualities using street view imagery (SVI) and computer vision (CV). Our analysis, employing linear regression and spatial regression models while controlling macro-environmental attributes as covariates, reveal the significant association between perceived design qualities and DBS cycling trip volume, confirming the significance of considering design qualities in DBS cycling studies. Geographically Weighted Regression (GWR) model explains the spatially heterogeneous effects of street-level attributes, offering practical suggestions for informing spatially varying policies and interventions for creating a cycling-friendly environment.
keywords	dockless bikeshare, street-level characteristics, urban design quality, street view imagery, semantic segmentation
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	ecaade2024_66
id	ecaade2024_66
authors	Jabi, Wassim; Li, Yang
year	2024
title	Graph Neural Networks for Node Classification and Attribute Allocation in Architectural BIM
doi	https://doi.org/10.52842/conf.ecaade.2024.1.675
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 1, pp. 675–684
summary	Building Information Modelling (BIM) marks a notable shift in architectural design, extending beyond simple digital reproductions by capturing the spatial, physical, and operational characteristics of structures. Unfortunately, these representations are often complex in nature and difficult to inspect, analyze, and understand which can lead to errors and omissions during model construction. This research aims to leverage graph machine learning systems, utilizing learned datasets, to detect and rectify these issues, improving model quality and minimizing costly mistakes. To illustrate the application of graph neural networks in this domain, this paper applied a graph-based geometric and topological editor coupled with a graph neural network to a real-world dataset of residential building complexes. The developed workflow operates by converting traditional architectural floor plans into graph-structured data, enabling precise node classification predictions. The paper details the overall workflow, data preparation and conversion, hyperparameter optimization and experimental results. Comparing the performance of various graph neural network models has validated the efficiency of the chosen prediction model in processing and analyzing architectural floor plans, achieving an overall accuracy rate of approximately 95%. The paper concludes with a discussion of the potential and limitations of graph-based machine learning methodologies within the architectural domain and an outline of future work plans.
keywords	Topology, Artificial Intelligence, Machine Learning, Graph Neural Network, Node Classification, Floor Plans
series	eCAADe
email
last changed	2024/11/17 22:05

_id	ecaade2024_180
id	ecaade2024_180
authors	Licen, Jurij; Chen, Taole
year	2024
title	Use of Genetic Optimisation Algorithms in the Design of 3D Concrete Printed Shell Structures
doi	https://doi.org/10.52842/conf.ecaade.2024.1.213
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 1, pp. 213–222
summary	A transition from disparate data to interconnected and contextually integrated data is currently causing a paradigm shift in the architecture industry. The need for fabrication-aware architectural representation models, that enable designers to interface with today's data-intensive manufacturing technologies, is a direct consequence of new concepts such as smart fabrication, automation and vertical integration. Compared to conventional concrete casting methods, 3D Concrete Printing (3DCP) offers a wide range of advantages, particularly the ability to create complex geometry. A lack of computational modelling techniques that link design and production for 3DCP is currently making it difficult to predict the printability of designs. This research presents a unified design-to-fabrication framework using machine learning (ML) that is customized for freeform steel-reinforced 3DCP shell structures. 3DCP is used to create incrementally cast sacrificial formwork. In particular, the segmentation process is fed back into the design process using genetic optimization for a fabrication-aware design model. The framework is validated with a series of physical experiments.
keywords	Additive Manufacturing, 3D Concrete Printing, Architectural Design, Integrated Workflow, Fabrication-Aware Modelling, Conceptual Design, Concrete Shells
series	eCAADe
email
last changed	2024/11/17 22:05

_id	ecaade2024_297
id	ecaade2024_297
authors	Massafra, Angelo; Coraglia, Ugo Maria; Predari, Giorgia; Gulli, Riccardo
year	2024
title	Building Information Model Analysis Through Large Language Models and Knowledge Graphs
doi	https://doi.org/10.52842/conf.ecaade.2024.1.685
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 1, pp. 685–694
summary	The advent of Large Language Models (LLMs) seems to mark a break between past and present in the methods of structuring knowledge, making it possible today to transfer this capability to machines even in a sector like AECO, always been information-intensive but resistant to technological transition. In terms of knowledge, the most established paradigm has been Building Information Modelling (BIM), with IFC functioning as the main schema for standardizing the industry's information. Added to this are knowledge graphs that, emerging with semantic web technologies, allow storing knowledge in structures consisting of nodes and edges with semantic meanings. Nevertheless, a barrier to the widespread adoption of BIM is its accessibility. Querying BIM models is often limited for stakeholders without digital skills, who may struggle to access the vast amount of information stored in these complex informative models. In an attempt to outline one of the possible uses of LLMs in BIM, this research proposes a method for querying BIM models through textual prompts aimed at analyzing a selected case study. In the workflow, a BIM model is first realized. Then, data is integrated into a knowledge graph. Next, ChatGPT's LLMs are used to activate query functions for the analysis of the graph. The results of the queries are displayed in a user-friendly graphical user interface. The study's outcomes offer insights for researchers and industry professionals, highlighting emerging research potentials for LLMs in the field.
keywords	Building Information Modeling, Large Language Models, Natural Language Processing, Knowledge Graphs
series	eCAADe
email
last changed	2024/11/17 22:05

_id	ecaade2024_310
id	ecaade2024_310
authors	Mosca, Caterina; D’Amico, Federico
year	2024
title	Data-driven Reduced-Order Models for Multidisciplinary Design Optimization Process
doi	https://doi.org/10.52842/conf.ecaade.2024.1.499
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 1, pp. 499–508
summary	Multidisciplinary Design Optimization (MDO) is a model-based simulation and optimization process that integrates multiple disciplines with conflicting objectives and design constraints to allow a more affordable design. In the Architecture, Engineering and Construction (AEC) sector this method still in the research and testing phase compared to the automotive and aerospace industries. However, the ability of MDO to extend the number of solutions examined through automation requires significant computational resources. In this context, the following paper explores the advantages of reducing simulation times using the AI-based reduced-order models (ROM). This data-driven method combines Artificial Intelligence and system modelling techniques to reduce computational complexity as Digital Twin (“As Designed”) and it can be used to speed up system design and optimization analyses. This paper presents a test application that explores how AI-based ROM can support the MDO process, which has already been applied to an AEC retrofit project. The case study is a classroom of an existing building where fluid dynamics, thermal and comfort performances have been optimized to support decisions in the conceptual design phase. Although the simulations were successful, a high computational complexity emerged, making it difficult to extend the simulations to the entire building and to more disciplines. The digital experiment carried out in this paper is about speeding up the process and making simulations easier compared to the legacy approach based on high computational simulations. The digital experiment carried out in this paper is about physics phenomena in buildings, which are only a part of the architecture performance and quality. This is an early example of demonstrating how AI-based ROMs can accelerate MDO simulations to make it scalable up the entire AEC design process in the future.
keywords	Multidisciplinary design Optimization, Reduced-order Model, Data-driven techniques, Machine learning, Energy simulation
series	eCAADe
email
last changed	2024/11/17 22:05

_id	ecaade2024_232
id	ecaade2024_232
authors	N. Panayiotou, Panayiotis; Kontovourkis, Odysseas
year	2024
title	A Holistic Documentation and Analysis of Timber Roof Structures in Heritage Buildings Using Scan to HBIM Approaches
doi	https://doi.org/10.52842/conf.ecaade.2024.1.715
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 1, pp. 715–724
summary	There is a great need for holistic documentation and management of heritage buildings using Historic Building Information Modelling (HBIM) frameworks. Limitations can be found in current literature regarding the accuracy, the level-of-detail, and the required attributes of final HBIM models, especially in cases where digital information intents to be used for the documentation of heritage timber roof structures. Previous research works indicate that geometry is created by the extrusion of the cross sections of the beams, and the usage of existing 2D drawings leading to simplified geometries in HBIM. This results in an absence of critical information, for example the bending of the wood, and its pathology. In this study, a novel Scan-to-HBIM methodology is exemplified and applied in heritage timber roof structures, which includes the implementation of recent remote sensing technologies for capturing the as-built data, with high levels of accuracy both in geometry as well as in pathology. In terms of geometry, algorithmic processes are used, that integrate parametric and BIM environments for the automatic creation of timber roof frames from point cloud data, which are adjustable to the abnormalities found in heritage buildings. As regards to pathology, high-resolution textured mesh models are created from photogrammetric procedures, which indicate in detail any possible defects to the existing timber elements. Detailed geometry and pathology are further analyzed, and a BIM database is created for documenting the typology, materiality, and level of damage to timber components. The methodology is tested on a Franko-Byzantine Timber roof Church in Cyprus, which includes a complex timber structural system.
keywords	Scan-to-HBIM, Terrestrial Laser Scanning, Photogrammetry, Algorithmic Design, Timber Roof Construction
series	eCAADe
email
last changed	2024/11/17 22:05

_id	ecaade2024_217
id	ecaade2024_217
authors	Panya, David Stephen; Kim, Taehoon; Heo, Minji; Choo, Seungyeon
year	2024
title	A BIM-based Virtual Reality Evacuation Simulation for Fire Safety Management
doi	https://doi.org/10.52842/conf.ecaade.2024.2.047
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 2, pp. 47–56
summary	In contemporary design and construction engineering, Building Information Modeling (BIM) technology significantly influences the evolution of fire safety. This research explores the intersection of fire safety and virtual reality (VR) by introducing an innovative emergency evacuation simulation method grounded in BIM technology. The study aims to establish a robust framework for emergency evacuation simulations by synthesizing fire dynamics, evacuation strategies, and BIM-based VR technologies. By bridging the theoretical-practical gap, the research endeavors to provide stakeholders in the construction industry with a toolset that prioritizes safety while enhancing designs for safer building projects. The study incorporates fire simulation utilizing CFAST, a representative zone model from the Korean National Institute of Standards and Technology. CFAST divides the fire room into high-temperature upper and low-temperature lower layers, assuming a uniform thermal and chemical environment. It interprets fire phenomena through principles such as mass conservation, the first law of thermodynamics, and the ideal gas equation. The study employs Cellular Automata (CA) to design an agent's reaction and behavior for evacuation. This involves creating a model based on CA rules, determining state changes, and designing behaviors accordingly. The study also focuses on formulating a calculation for evacuation time, refining it based on key factors. The integration of CFAST and CA, along with models for fire and evacuation simulations, enhances the accuracy and utility of evacuation simulations. The research introduces computational models and BIM models in a visually immersive experience in VR across 3 types of fire emergency scenarios.
keywords	BIM, Virtual Reality, Evacuation Simulation, Fire Safety Management
series	eCAADe
email
last changed	2024/11/17 22:05

_id	architectural_intelligence2024_1
id	architectural_intelligence2024_1
authors	Runmin Zhao, Junjie Liu, Nan Jiang & Sumei Liu
year	2024
title	Wind tunnel and numerical study of outdoor particle dispersion around a low-rise building model
doi	https://doi.org/https://doi.org/10.1007/s44223-023-00045-w
source	Architectural Intelligence Journal
summary	The dispersion of particulate pollutants around buildings raises concerns due to adverse health impacts. Accurate prediction of particle dispersion is important for evaluating health risks in urban areas. However, rigorous validation data using particulate tracers is lacking for numerical models of urban dispersion. Many prior studies rely on gas dispersion data, questioning conclusions due to differences in transport physics. To address this gap, this study utilized a combined experimental and computational approach to generate comprehensive validation data on particulate dispersion. A wind tunnel experiment using particulate tracers measured airflow, turbulence, and particle concentrations around a single building, providing reliable but sparse data. Validated large eddy simulation expanded the data. This combined approach generated much-needed validation data to evaluate numerical particle dispersion models around buildings. Steady Reynolds-averaged Navier–Stokes (SRANS) simulations paired with Lagrangian particle tracking (LPT), and drift-flux (DF) models were validated. SRANS had lower accuracy compared to LES for airflow and turbulence. However, in this case, SRANS inaccuracies did not prevent accurate concentration prediction when LPT or a Stokes drift-flux model were used. The algebraic drift-flux model strongly overpredicted the concentration for large micron particles, indicating proper drift modeling was essential.
series	Architectural Intelligence
email
last changed	2025/01/09 15:03

_id	ecaade2024_117
id	ecaade2024_117
authors	Su, Xinyu; Luo, Jianhe; Liu, Zidong; Yan, Gaoliang
year	2024
title	Text to Terminal: A framework for generating airport terminal layout with large-scale language-image models
doi	https://doi.org/10.52842/conf.ecaade.2024.1.469
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 1, pp. 469–478
summary	Large-scale language-image (LLI) models present novel opportunities for architectural design by facilitating its multimodal process via text-image interactions. However, the inherent two-dimensionality of their outputs restricts their utility in architectural practice. Airport terminals, characterized by their flexibility and patterned forms, with most of the design operations occurring at the level of master plan, indicating a promising application area for LLI models. We propose a workflow that, in the early design phase, employs a fine-tuned Stable Diffusion model to generate terminal design solutions from textual descriptions and a site image, followed by a quantitative evaluation from an architectural expert's viewpoint. We created our dataset by collecting satellite images of 295 airport terminals worldwide and annotating them in terms of size and form. Using Terminal 2 of Zhengzhou Xinzheng International Airport as a case study, we scored the original and generated solutions on three airside evaluation metrics, verifying the validity of the proposed method. Our study bridges image generation and expert architectural design assessments, providing valuable insights into the practical application of LLI models in architectural practice and introducing a new method for the intelligent design of large-scale public buildings.
keywords	Multimodal Machine Learning, Diffusion Model, Text-to-Architecture, Airport Terminal Configuration Design, Post-Generation Evaluation
series	eCAADe
email
last changed	2024/11/17 22:05

For more results click below: